##Introduction

There has tremendous growth in the area undergraduate biology research over the last two decades. This study attempts to summarize and analyze the progress of this growth.

Summary of initial data set

This is a placeholder for the inital data set Whole group

txt <- c("rawdata/CBE_LSE_2010-2019/20200717_CBE2010-2019-WOS-1-500.txt",
         "rawdata/CBE_LSE_2010-2019/20200717_CBE2010-2019-WOS-501-708.txt")
data <- convert2df(file = txt, dbsource = 'wos', format = "plaintext")
## 
## Converting your wos collection into a bibliographic dataframe
## 
## 
## Warning:
## In your file, some mandatory metadata are missing. Bibliometrix functions may not work properly!
## 
## Please, take a look at the vignettes:
## - 'Data Importing and Converting' (https://cran.r-project.org/web/packages/bibliometrix/vignettes/Data-Importing-and-Converting.html)
## - 'A brief introduction to bibliometrix' (https://cran.r-project.org/web/packages/bibliometrix/vignettes/bibliometrix-vignette.html)
## 
## 
## Missing fields:  DEDone!
## 
## 
## Generating affiliation field tag AU_UN from C1:  Done!
results <- biblioAnalysis(data, sep = ";")
options(width=100)

S <- summary(object = results, k = 10, pause = FALSE)
## 
## 
## MAIN INFORMATION ABOUT DATA
## 
##  Timespan                              2010 : 2019 
##  Sources (Journals, Books, etc)        1 
##  Documents                             708 
##  Average years from publication        4.97 
##  Average citations per documents       14.12 
##  Average citations per year per doc    2.044 
##  References                            18276 
##  
## DOCUMENT TYPES                     
##  article         656 
##  correction      18 
##  letter          30 
##  review          4 
##  
## DOCUMENT CONTENTS
##  Keywords Plus (ID)                    983 
##  Author's Keywords (DE)                0 
##  
## AUTHORS
##  Authors                               2295 
##  Author Appearances                    3255 
##  Authors of single-authored documents  59 
##  Authors of multi-authored documents   2236 
##  
## AUTHORS COLLABORATION
##  Single-authored documents             70 
##  Documents per Author                  0.308 
##  Authors per Document                  3.24 
##  Co-Authors per Documents              4.6 
##  Collaboration Index                   3.5 
##  
## 
## Annual Scientific Production
## 
##  Year    Articles
##     2010       59
##     2011       40
##     2012       50
##     2013       76
##     2014       71
##     2015       58
##     2016      105
##     2017       84
##     2018       84
##     2019       81
## 
## Annual Percentage Growth Rate 3.583971 
## 
## 
## Most Productive Authors
## 
##    Authors        Articles Authors        Articles Fractionalized
## 1    TANNER KD          23   TANNER KD                      10.81
## 2    BROWNELL SE        21   BROWNELL SE                     5.92
## 3    KNIGHT JK          21   KNIGHT JK                       5.59
## 4    SMITH MK           17   [ANONYMOUS]                     5.00
## 5    DOLAN EL           16   ALLEN D                         4.14
## 6    ANDREWS TC         11   BRAME CJ                        3.83
## 7    COUCH BA           11   SMITH MK                        3.78
## 8    CORWIN LA          10   DOLAN EL                        3.60
## 9    EDDY SL            10   ANDREWS TC                      3.14
## 10   WENDEROTH MP       10   SCHUSSLER EE                    2.68
## 
## 
## Top manuscripts per citations
## 
##                             Paper           TC TCperYear
## 1  AUCHINCLOSS LC, 2014, CBE-LIFE SCI EDUC 216      30.9
## 2  JENSEN JL, 2015, CBE-LIFE SCI EDUC      215      35.8
## 3  BROWNELL SE, 2012, CBE-LIFE SCI EDUC    163      18.1
## 4  ANDREWS TM, 2011, CBE-LIFE SCI EDUC     154      15.4
## 5  EDDY SL, 2014, CBE-LIFE SCI EDUC        134      19.1
## 6  MORAVEC M, 2010, CBE-LIFE SCI EDUC      130      11.8
## 7  MAHER JM, 2013, CBE-LIFE SCI EDUC       127      15.9
## 8  TANNER KD, 2012, CBE-LIFE SCI EDUC      125      13.9
## 9  SMITH MK, 2013, CBE-LIFE SCI EDUC       117      14.6
## 10 SMITH MK, 2011, CBE-LIFE SCI EDUC-a     112      11.2
## 
## 
## Corresponding Author's Countries
## 
##           Country Articles    Freq SCP MCP MCP_Ratio
## 1  USA                 638 0.92464 615  23    0.0361
## 2  CANADA               16 0.02319  13   3    0.1875
## 3  AUSTRALIA             4 0.00580   4   0    0.0000
## 4  NETHERLANDS           4 0.00580   4   0    0.0000
## 5  SWEDEN                4 0.00580   2   2    0.5000
## 6  GERMANY               3 0.00435   2   1    0.3333
## 7  ISRAEL                2 0.00290   2   0    0.0000
## 8  NEW ZEALAND           2 0.00290   1   1    0.5000
## 9  NORWAY                2 0.00290   2   0    0.0000
## 10 UNITED KINGDOM        2 0.00290   2   0    0.0000
## 
## 
## SCP: Single Country Publications
## 
## MCP: Multiple Country Publications
## 
## 
## Total Citations per Country
## 
##      Country      Total Citations Average Article Citations
## 1  USA                       9534                     14.94
## 2  CANADA                     127                      7.94
## 3  NETHERLANDS                 79                     19.75
## 4  SWEDEN                      78                     19.50
## 5  AUSTRALIA                   60                     15.00
## 6  ISRAEL                      18                      9.00
## 7  SLOVENIA                    14                     14.00
## 8  CHINA                       13                     13.00
## 9  CZECH REPUBLIC              13                     13.00
## 10 FRANCE                      13                     13.00
## 
## 
## Most Relevant Sources
## 
##                Sources        Articles
## 1 CBE-LIFE SCIENCES EDUCATION      708
S
## $MainInformation
##  [1] "\n\nMAIN INFORMATION ABOUT DATA\n\n"                  "Timespan                              2010 : 2019 \n"
##  [3] "Sources (Journals, Books, etc)        1 \n"           "Documents                             708 \n"        
##  [5] "Average years from publication        4.97 \n"        "Average citations per documents       14.12 \n"      
##  [7] "Average citations per year per doc    2.044 \n"       "References                            18276 \n"      
##  [9] "\nDOCUMENT TYPES                     \n"              "article         656 \n"                              
## [11] "correction      18 \n"                                "letter          30 \n"                               
## [13] "review          4 \n"                                 "\nDOCUMENT CONTENTS\n"                               
## [15] "Keywords Plus (ID)                    983 \n"         "Author's Keywords (DE)                0 \n"          
## [17] "\nAUTHORS\n"                                          "Authors                               2295 \n"       
## [19] "Author Appearances                    3255 \n"        "Authors of single-authored documents  59 \n"         
## [21] "Authors of multi-authored documents   2236 \n"        "\nAUTHORS COLLABORATION\n"                           
## [23] "Single-authored documents             70 \n"          "Documents per Author                  0.308 \n"      
## [25] "Authors per Document                  3.24 \n"        "Co-Authors per Documents              4.6 \n"        
## [27] "Collaboration Index                   3.5 \n"         "\n"                                                  
## 
## $MainInformationDF
##                             Description   Results
## 1           MAIN INFORMATION ABOUT DATA          
## 2                              Timespan 2010:2019
## 3        Sources (Journals, Books, etc)         1
## 4                             Documents       708
## 5        Average years from publication      4.97
## 6       Average citations per documents     14.12
## 7    Average citations per year per doc     2.044
## 8                            References     18276
## 9                        DOCUMENT TYPES          
## 10                              article       656
## 11                           correction        18
## 12                               letter        30
## 13                               review         4
## 14                    DOCUMENT CONTENTS          
## 15                   Keywords Plus (ID)       983
## 16               Author's Keywords (DE)         0
## 17                              AUTHORS          
## 18                              Authors      2295
## 19                   Author Appearances      3255
## 20 Authors of single-authored documents        59
## 21  Authors of multi-authored documents      2236
## 22                AUTHORS COLLABORATION          
## 23            Single-authored documents        70
## 24                 Documents per Author     0.308
## 25                 Authors per Document      3.24
## 26             Co-Authors per Documents       4.6
## 27                  Collaboration Index       3.5
## 28                                               
## 
## $AnnualProduction
##    Year    Articles
## 1     2010       59
## 2     2011       40
## 3     2012       50
## 4     2013       76
## 5     2014       71
## 6     2015       58
## 7     2016      105
## 8     2017       84
## 9     2018       84
## 10    2019       81
## 
## $AnnualGrowthRate
## [1] 3.583971
## 
## $MostProdAuthors
##    Authors        Articles Authors        Articles Fractionalized
## 1    TANNER KD          23   TANNER KD                      10.81
## 2    BROWNELL SE        21   BROWNELL SE                     5.92
## 3    KNIGHT JK          21   KNIGHT JK                       5.59
## 4    SMITH MK           17   [ANONYMOUS]                     5.00
## 5    DOLAN EL           16   ALLEN D                         4.14
## 6    ANDREWS TC         11   BRAME CJ                        3.83
## 7    COUCH BA           11   SMITH MK                        3.78
## 8    CORWIN LA          10   DOLAN EL                        3.60
## 9    EDDY SL            10   ANDREWS TC                      3.14
## 10   WENDEROTH MP       10   SCHUSSLER EE                    2.68
## 
## $MostCitedPapers
##                             Paper           TC TCperYear
## 1  AUCHINCLOSS LC, 2014, CBE-LIFE SCI EDUC 216      30.9
## 2  JENSEN JL, 2015, CBE-LIFE SCI EDUC      215      35.8
## 3  BROWNELL SE, 2012, CBE-LIFE SCI EDUC    163      18.1
## 4  ANDREWS TM, 2011, CBE-LIFE SCI EDUC     154      15.4
## 5  EDDY SL, 2014, CBE-LIFE SCI EDUC        134      19.1
## 6  MORAVEC M, 2010, CBE-LIFE SCI EDUC      130      11.8
## 7  MAHER JM, 2013, CBE-LIFE SCI EDUC       127      15.9
## 8  TANNER KD, 2012, CBE-LIFE SCI EDUC      125      13.9
## 9  SMITH MK, 2013, CBE-LIFE SCI EDUC       117      14.6
## 10 SMITH MK, 2011, CBE-LIFE SCI EDUC-a     112      11.2
## 
## $MostProdCountries
##           Country Articles    Freq SCP MCP MCP_Ratio
## 1  USA                 638 0.92464 615  23    0.0361
## 2  CANADA               16 0.02319  13   3    0.1875
## 3  AUSTRALIA             4 0.00580   4   0    0.0000
## 4  NETHERLANDS           4 0.00580   4   0    0.0000
## 5  SWEDEN                4 0.00580   2   2    0.5000
## 6  GERMANY               3 0.00435   2   1    0.3333
## 7  ISRAEL                2 0.00290   2   0    0.0000
## 8  NEW ZEALAND           2 0.00290   1   1    0.5000
## 9  NORWAY                2 0.00290   2   0    0.0000
## 10 UNITED KINGDOM        2 0.00290   2   0    0.0000
## 
## $TCperCountries
##      Country      Total Citations Average Article Citations
## 1  USA                       9534                     14.94
## 2  CANADA                     127                      7.94
## 3  NETHERLANDS                 79                     19.75
## 4  SWEDEN                      78                     19.50
## 5  AUSTRALIA                   60                     15.00
## 6  ISRAEL                      18                      9.00
## 7  SLOVENIA                    14                     14.00
## 8  CHINA                       13                     13.00
## 9  CZECH REPUBLIC              13                     13.00
## 10 FRANCE                      13                     13.00
## 
## $MostRelSources
##                Sources        Articles
## 1 CBE-LIFE SCIENCES EDUCATION      708
## 
## $MostRelKeywords
## NULL
plot(x=results, k=10, pause=F)

## Warning: Use of `xx$Country` is discouraged. Use `Country` instead.
## Warning: Use of `xx$Freq` is discouraged. Use `Freq` instead.
## Warning: Use of `xx$Collaboration` is discouraged. Use `Collaboration` instead.

## Warning: Use of `Y$Year` is discouraged. Use `Year` instead.
## Warning: Use of `Y$Freq` is discouraged. Use `Freq` instead.
## Warning: Use of `Y$Year` is discouraged. Use `Year` instead.
## Warning: Use of `Y$Freq` is discouraged. Use `Freq` instead.

## Warning: Use of `Table2$Year` is discouraged. Use `Year` instead.
## Warning: Use of `Table2$MeanTCperYear` is discouraged. Use `MeanTCperYear` instead.
## Warning: Use of `Table2$Year` is discouraged. Use `Year` instead.
## Warning: Use of `Table2$MeanTCperYear` is discouraged. Use `MeanTCperYear` instead.

## Warning: Use of `Table2$Year` is discouraged. Use `Year` instead.
## Warning: Use of `Table2$MeanTCperArt` is discouraged. Use `MeanTCperArt` instead.
## Warning: Use of `Table2$Year` is discouraged. Use `Year` instead.
## Warning: Use of `Table2$MeanTCperArt` is discouraged. Use `MeanTCperArt` instead.

S$MainInformationDF
##                             Description   Results
## 1           MAIN INFORMATION ABOUT DATA          
## 2                              Timespan 2010:2019
## 3        Sources (Journals, Books, etc)         1
## 4                             Documents       708
## 5        Average years from publication      4.97
## 6       Average citations per documents     14.12
## 7    Average citations per year per doc     2.044
## 8                            References     18276
## 9                        DOCUMENT TYPES          
## 10                              article       656
## 11                           correction        18
## 12                               letter        30
## 13                               review         4
## 14                    DOCUMENT CONTENTS          
## 15                   Keywords Plus (ID)       983
## 16               Author's Keywords (DE)         0
## 17                              AUTHORS          
## 18                              Authors      2295
## 19                   Author Appearances      3255
## 20 Authors of single-authored documents        59
## 21  Authors of multi-authored documents      2236
## 22                AUTHORS COLLABORATION          
## 23            Single-authored documents        70
## 24                 Documents per Author     0.308
## 25                 Authors per Document      3.24
## 26             Co-Authors per Documents       4.6
## 27                  Collaboration Index       3.5
## 28
write.csv(file = "keywords.csv",as.data.frame(results$ID[1:20]))

write.csv(file = "Maininformation.csv",S$MainInformationDF)

write.csv(file = "ArticlesYears.csv",S$AnnualProduction)

write.csv(file = "MostCitedPapers.csv",S$MostCitedPapers)

write.csv(file = "MostProdAuthors.csv", S$MostProdAuthors)

##Authoring

authors=gsub(","," ",names(results$Authors)[1:10])

indices <- Hindex(data, field = "author", elements=authors, sep = ";", years = 50)

indices$H
##          Author h_index g_index   m_index  TC NP PY_start
## 1     TANNER KD      11      23 1.0000000 667 23     2010
## 2   BROWNELL SE      10      21 1.1111111 566 21     2012
## 3     KNIGHT JK       9      20 0.8181818 416 21     2010
## 4      SMITH MK       9      17 0.8181818 424 17     2010
## 5      DOLAN EL      11      16 1.0000000 604 16     2010
## 6    ANDREWS TC       5      10 0.7142857 115 11     2014
## 7      COUCH BA       6      10 1.0000000 110 11     2015
## 8     CORWIN LA       5      10 0.8333333 170 10     2015
## 9       EDDY SL       7      10 1.0000000 373 10     2014
## 10 WENDEROTH MP       7      10 0.6363636 318 10     2010
avgAU <- as.data.frame(cbind(results[["nAUperPaper"]],results[["Years"]])) 
colnames(avgAU) <-c("nAu","Years")
avgAUres<-avgAU %>%
  mutate(Years = as.factor(Years)) %>%
  group_by(Years) %>%
  summarize(avg = mean(nAu), med = median(nAu))
## `summarise()` ungrouping output (override with `.groups` argument)
lm(nAu ~ Years, avgAU %>% mutate(Years = Years - 2010))
## 
## Call:
## lm(formula = nAu ~ Years, data = avgAU %>% mutate(Years = Years - 
##     2010))
## 
## Coefficients:
## (Intercept)        Years  
##      3.8091       0.1567
ggplot(avgAU,aes(Years,nAu)) + 
  geom_point() +
  geom_smooth()
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

ggplot(avgAUres,aes(x = Years, y = med)) + 
  geom_point() +
  geom_smooth()
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

Research Questions

Social Network Analysis (SNA) of co-authorship: What social structures are organizing co-authorship?

Rachel Kudlacz This is the placeholder for the question about the social struction of co-authorship the among the CBE-LSE authors. A social network analysis approach was used… Text to introduce the script and outputs

## Warning in closeness(bsk.network): At centrality.c:2784 :closeness centrality is not well-defined for disconnected
## graphs

Text to explain what is shown in the figures.

What are the collaborative connections between institutions?

Germaine Ng

This is the placeholder for the question about collaborations between different universities (institutions) Text to introduce the script and outputs

Affiliation=results$Affiliations[1:20]
Affiliation
## AFF
##      MICHIGAN STATE UNIV            UNIV COLORADO             UNIV GEORGIA          UNIV WASHINGTON 
##                       83                       67                       65                       58 
##           UNIV WISCONSIN SAN FRANCISCO STATE UNIV              PURDUE UNIV   UNIV CALIF LOS ANGELES 
##                       53                       44                       37                       37 
##          WASHINGTON UNIV       ARIZONA STATE UNIV    UNIV BRITISH COLUMBIA                DUKE UNIV 
##                       35                       33                       30                       29 
##            UNIV NEBRASKA               EMORY UNIV        UNIV TEXAS AUSTIN     UNIV CALIF SAN DIEGO 
##                       26                       24                       24                       23 
##            UNIV MARYLAND           UNIV MINNESOTA          VANDERBILT UNIV                YALE UNIV 
##                       23                       23                       23                       23
Aff_Freq=results[["Aff_frac"]] %>%
  arrange(desc(Frequency))%>%
  top_n(10)
## Selecting by Frequency
Aff_Freq
##                 Affiliation Frequency
## 1       MICHIGAN STATE UNIV 24.805700
## 2             UNIV COLORADO 23.977510
## 3              UNIV GEORGIA 22.598521
## 4           UNIV WASHINGTON 21.628175
## 5  SAN FRANCISCO STATE UNIV 17.965443
## 6        ARIZONA STATE UNIV 14.793254
## 7            UNIV WISCONSIN 14.505231
## 8               PURDUE UNIV 10.394051
## 9     UNIV BRITISH COLUMBIA 10.083333
## 10           UNIV MINNESOTA  9.596825
## Warning in closeness(bsk.network): At centrality.c:2784 :closeness centrality is not well-defined for disconnected
## graphs

## san francisco state univ          washington univ            univ colorado            grinnell coll 
##                      342                      266                      222                      219 
##     univ calif san diego                duke univ 
##                      214                      210
## Warning in closeness(bsk.network): At centrality.c:2784 :closeness centrality is not well-defined for disconnected
## graphs

What is the intellectual structures? Document co-citation network and topic analysis

Darcie Nelson

library(stringdist)
## 
## Attaching package: 'stringdist'
## The following object is masked from 'package:tidyr':
## 
##     extract
library(stringr)
library(stringi)
library(plyr)
## ----------------------------------------------------------------------------------------------------------------------
## You have loaded plyr after dplyr - this is likely to cause problems.
## If you need functions from both plyr and dplyr, please load plyr first, then dplyr:
## library(plyr); library(dplyr)
## ----------------------------------------------------------------------------------------------------------------------
## 
## Attaching package: 'plyr'
## The following objects are masked from 'package:dplyr':
## 
##     arrange, count, desc, failwith, id, mutate, rename, summarise, summarize
## The following object is masked from 'package:purrr':
## 
##     compact
library(dplyr)
library(magrittr)
## 
## Attaching package: 'magrittr'
## The following object is masked from 'package:stringdist':
## 
##     extract
## The following object is masked from 'package:purrr':
## 
##     set_names
## The following object is masked from 'package:tidyr':
## 
##     extract
library(broom)
library(lazyeval)
## 
## Attaching package: 'lazyeval'
## The following objects are masked from 'package:purrr':
## 
##     is_atomic, is_formula
library(tidyr)
library(reshape2)
## 
## Attaching package: 'reshape2'
## The following object is masked from 'package:tidyr':
## 
##     smiths
library(data.table)
## 
## Attaching package: 'data.table'
## The following objects are masked from 'package:reshape2':
## 
##     dcast, melt
## The following objects are masked from 'package:dplyr':
## 
##     between, first, last
## The following object is masked from 'package:purrr':
## 
##     transpose
#citations

# load functions
  source("cleaningfunctions/citation_functions.R")


# Extract citations from WOS list
    work_data <- as.data.frame(extract_citation(data, "CR"))
## Warning in melt(citations): The melt generic in data.table has been passed a list and will attempt to redirect to the
## relevant reshape2 method; please note that reshape2 is deprecated, and this redirection is now deprecated as well.
## To continue using melt methods from reshape2 while both libraries are attached, e.g. melt.list, you can prepend the
## namespace like reshape2::melt(citations). In the next version, this warning will become an error.
    #work_data$label <- as.character(work_data$label)
    work_data$L1<- as.factor(work_data$L1)
    work_data$index<-as.factor( work_data$index)

# Standardize the data--------------------------------------------------------------------
   std_data <- standardize(work_data)

# show authors who are longer than 50 characters
   author_temp <- std_data %>%
        select(authors) %>%
        filter(nchar(authors) > 50)

# clean and standardize author names -----------------------------------------------------

# Run fuzzy match function on a .2 threshold

    std_data$authorBlock <- fuzzy_match(std_data$authors, .1, std_data$authors)

   # look at author clusters
    author_merges <- std_data %>%
      group_by(authorBlock) %>%
      dplyr::summarise(count = n()) %>%
      filter(count > 15) %>%
      arrange(desc(count))
## `summarise()` ungrouping output (override with `.groups` argument)
    # Run the clustering algorithm again to recluster top merge
    # get the top merged author
    name <- author_merges[1, ][[1]]

    std_data2 <- std_data %>%
      filter(authorBlock == name) %>%
      mutate(authorBlock = fuzzy_match(authors, .08, authors))

    std_data3 <- std_data %>%
      filter(authorBlock != name) %>%
      bind_rows(std_data2)

    std_data4 <- std_data3 %>%
      filter(authorBlock == name) %>%
      mutate(authorBlock = fuzzy_match(authors, .05, authors))

    std_data5 <- std_data3 %>%
      filter(authorBlock != name) %>%
      bind_rows(std_data4)

#Add specific criteria for problematic author names
    std_data5$authorBlock[grep("assaraf", std_data5$authorBlock)]
## [1] "assaraf obz" "assaraf obz" "assaraf obz" "assaraf obz"
# Run clustering algorithm----------------------------------------------------------------
    books <- std_data5 %>%
        group_by(authorBlock, documentName, documentYear) %>%
        filter(type == "book") %>%
        mutate(mergedLabel = fuzzy_match(cleanLabel, .05, cleanLabel))

    articles <- std_data5 %>%
        group_by(authorBlock, documentName, documentYear) %>%
        filter(type == "article") %>%
        mutate(mergedLabel = fuzzy_match(cleanLabel, .01, cleanLabel))

        clean_data <- rbind(books, articles)


# create the flat data file
    
    flat_data<- as.data.table(clean_data)[, toString(paste0(mergedLabel,collapse = ";")), by = list(L1)]



# make sure to unwrap this again to check if it was wrapped properly
    rownames(flat_data) <- as.character(flat_data$L1)
                                         
    flat_data2 <- inner_join(data, flat_data, by = c("SR" = "L1"))
    flat_data2$CR <- flat_data2$V1
# find the similarity  of the merges------------------------------------------------------

    clean_data <- clean_data %>%
        mutate(jwSimilarity = calc_jw(cleanLabel, mergedLabel))


# plot------------------------------------------------------------------------------------

    merged <- clean_data %>%
        filter(jwSimilarity < 1)

    hist(round(merged$jwSimilarity, 3),
         xlab = "jw similarity distance",
         main = "Freq Merges by similarity distance \n with year and document type boundary")

# save the data------------------------------------------------------------------------------------
    write.csv(clean_data, "WOS_nodeList.csv", row.names = FALSE)
    write.csv(flat_data2, "WOS_clean.csv", row.names = FALSE)

CR <- citations(data, field = "article", sep = ";")
CRtable <-cbind(CR$Cited[1:20])
CRtable
##                                                                                 [,1]
## AMERICAN ASSOCIATION FOR THE ADVANCEMENT OF SCIENCE, 2011, VIS CHANG UND BIOL E  159
## FREEMAN S, 2014, P NATL ACAD SCI USA, V111, P8410, DOI 10.1073/PNAS.1319030111   105
## [ANONYMOUS], 2012, ENG EXC PROD ON MILL                                           75
## CROWE A, 2008, CBE-LIFE SCI EDUC, V7, P368, DOI 10.1187/CBE.08-05-0024            70
## HANDELSMAN J, 2004, SCIENCE, V304, P521, DOI 10.1126/SCIENCE.1096022              62
## SMITH MK, 2008, CBE-LIFE SCI EDUC, V7, P422, DOI 10.1187/CBE.08-08-0045           62
## HAAK DC, 2011, SCIENCE, V332, P1213, DOI 10.1126/SCIENCE.1204820                  54
## SEYMOUR E., 1997, TALKING LEAVING WHY                                             51
## FREEMAN SCOTT, 2007, CBE LIFE SCI EDUC, V6, P132, DOI 10.1187/CBE.06-09-0194      50
## EBERT-MAY D, 2011, BIOSCIENCE, V61, P550, DOI 10.1525/BIO.2011.61.7.9             49
## EDDY SL, 2014, CBE-LIFE SCI EDUC, V13, P453, DOI 10.1187/CBE.14-03-0050           49
## HAKE RR, 1998, AM J PHYS, V66, P64, DOI 10.1119/1.18809                           49
## KNIGHT JENNIFER K, 2005, CELL BIOL EDUC, V4, P298, DOI 10.1187/05-06-0082         49
## SEYMOUR E, 2004, SCI EDUC, V88, P493, DOI 10.1002/SCE.10131                       48
## HENDERSON C, 2011, J RES SCI TEACH, V48, P952, DOI 10.1002/TEA.20439              47
## RUSSELL SH, 2007, SCIENCE, V316, P548, DOI 10.1126/SCIENCE.1140384                47
## ANDERSON DL, 2002, J RES SCI TEACH, V39, P952, DOI 10.1002/TEA.10053              44
## LOPATTO DAVID, 2007, CBE LIFE SCI EDUC, V6, P297, DOI 10.1187/CBE.07-06-0039      44
## NATIONAL RESEARCH COUNCIL, 2003, BIO2010 TRANSF UND E                             44
## AUCHINCLOSS LC, 2014, CBE-LIFE SCI EDUC, V13, P29, DOI 10.1187/CBE.14-01-0004     43
CR2 <- citations(flat_data2, field = "article", sep = ";")
CR2table <-cbind(CR2$Cited[1:20])
CR2table
##                                                                                 [,1]
## american association for the advancement of science, 2011, vis chang und biol e  185
## freeman s, 2014, p natl acad sci usa, v111, p8410                                105
## anonymous, 2012, eng exc prod on mill                                             75
## crowe a, 2008, cbelife sci educ, v7, p368                                         70
## handelsman j, 2004, science, v304, p521                                           62
## smith mk, 2008, cbelife sci educ, v7, p422                                        62
## seymour e, 1997, talking leaving why                                              59
## haak dc, 2011, science, v332, p1213                                               54
## freeman scott, 2007, cbe life sci educ, v6, p132                                  50
## ebertmay d, 2011, bioscience, v61, p550                                           49
## eddy sl, 2014, cbelife sci educ, v13, p453                                        49
## hake rr, 1998, am j phys, v66, p64                                                49
## handelsman j, 2007, sci teaching                                                  49
## knight jennifer k, 2005, cell biol educ, v4, p298                                 49
## seymour e, 2004, sci educ, v88, p493                                              48
## henderson c, 2011, j res sci teach, v48, p952                                     47
## national research council, 2003, bio2010 transf und e                             47
## russell sh, 2007, science, v316, p548                                             47
## anderson dl, 2002, j res sci teach, v39, p952                                     44
## lopatto david, 2007, cbe life sci educ, v6, p297                                  44
write.csv(file = "Citations.csv",CR2table)

sourcestable <-cbind(summary(factor(CR$Source))
[1:10])
sourcestable
##                      [,1]
## CBE-LIFE SCI EDUC     561
## J RES SCI TEACH       393
## SCIENCE               263
## J COLL SCI TEACH      235
## INT J SCI EDUC        205
## SCI EDUC              203
## J CHEM EDUC           188
## J EDUC PSYCHOL        159
## AM BIOL TEACH         149
## BIOCHEM MOL BIOL EDU  110
write.csv(file = "Sources.csv",sourcestable)
## Warning in closeness(bsk.network): At centrality.c:2784 :closeness centrality is not well-defined for disconnected
## graphs

CS <- conceptualStructure(data,field ="ID", method = "MCA", minDegree=19, clust= 4 ,k.max=20, stemming=TRUE, labelsize=10, documents=10)

## Warning: Use of `A$dim1` is discouraged. Use `dim1` instead.
## Warning: Use of `A$dim2` is discouraged. Use `dim2` instead.
## Warning: Use of `A$nomi` is discouraged. Use `nomi` instead.
## Warning: Use of `A$dim1` is discouraged. Use `dim1` instead.
## Warning: Use of `A$dim2` is discouraged. Use `dim2` instead.
## Warning: Use of `A$nomi` is discouraged. Use `nomi` instead.

## Warning: Use of `B$dim1` is discouraged. Use `dim1` instead.
## Warning: Use of `B$dim2` is discouraged. Use `dim2` instead.
## Warning: Use of `B$nomi` is discouraged. Use `nomi` instead.
## Warning: Use of `B$dim1` is discouraged. Use `dim1` instead.
## Warning: Use of `B$dim2` is discouraged. Use `dim2` instead.
## Warning: Use of `B$nomi` is discouraged. Use `nomi` instead.

#CS4 <- conceptualStructure(data,field ="ID", method = "MCA", minDegree=6, clust= "auto" ,k.max=20, stemming=TRUE, labelsize=4, documents=10)

ggsave("ConceptualStructure.png", plot = CS$graph_terms, device = "png")
## Saving 7 x 5 in image